Techniques for Detecting Text

In some examples, a system for detecting text in an image includes a memory device to store a text detection model trained using images of up-scaled text, and a processor configured to perform text detection on an image to generate original bounding boxes that identify potential text in the image. T...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: BARZELAY, Udi, AZULAI, Ophir, NAPARSTEK, Oshri Pesah
Format: Patent
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator BARZELAY, Udi
AZULAI, Ophir
NAPARSTEK, Oshri Pesah
description In some examples, a system for detecting text in an image includes a memory device to store a text detection model trained using images of up-scaled text, and a processor configured to perform text detection on an image to generate original bounding boxes that identify potential text in the image. The processor is also configured to generate a secondary image that includes up-scaled portions of the image associated with bounding boxes below a threshold size, and perform text detection on the secondary image to generate secondary bounding boxes that identify potential text in the secondary image. The processor is also configured to compare the original bounding boxes with the secondary bounding boxes to identify original bounding boxes that are false positives, and generate an image file that includes the original bounding boxes, wherein those original bounding boxes that are identified as false positives are removed.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2023196807A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2023196807A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2023196807A13</originalsourceid><addsrcrecordid>eNrjZJANSU3OyMssLE0tVkjLL1JwSS1JTS7JzEtXCEmtKOFhYE1LzClO5YXS3AzKbq4hzh66qQX58anFBYnJqXmpJfGhwUYGRsaGlmYWBuaOhsbEqQIAU_QlAA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Techniques for Detecting Text</title><source>esp@cenet</source><creator>BARZELAY, Udi ; AZULAI, Ophir ; NAPARSTEK, Oshri Pesah</creator><creatorcontrib>BARZELAY, Udi ; AZULAI, Ophir ; NAPARSTEK, Oshri Pesah</creatorcontrib><description>In some examples, a system for detecting text in an image includes a memory device to store a text detection model trained using images of up-scaled text, and a processor configured to perform text detection on an image to generate original bounding boxes that identify potential text in the image. The processor is also configured to generate a secondary image that includes up-scaled portions of the image associated with bounding boxes below a threshold size, and perform text detection on the secondary image to generate secondary bounding boxes that identify potential text in the secondary image. The processor is also configured to compare the original bounding boxes with the secondary bounding boxes to identify original bounding boxes that are false positives, and generate an image file that includes the original bounding boxes, wherein those original bounding boxes that are identified as false positives are removed.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2023</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230622&amp;DB=EPODOC&amp;CC=US&amp;NR=2023196807A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230622&amp;DB=EPODOC&amp;CC=US&amp;NR=2023196807A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>BARZELAY, Udi</creatorcontrib><creatorcontrib>AZULAI, Ophir</creatorcontrib><creatorcontrib>NAPARSTEK, Oshri Pesah</creatorcontrib><title>Techniques for Detecting Text</title><description>In some examples, a system for detecting text in an image includes a memory device to store a text detection model trained using images of up-scaled text, and a processor configured to perform text detection on an image to generate original bounding boxes that identify potential text in the image. The processor is also configured to generate a secondary image that includes up-scaled portions of the image associated with bounding boxes below a threshold size, and perform text detection on the secondary image to generate secondary bounding boxes that identify potential text in the secondary image. The processor is also configured to compare the original bounding boxes with the secondary bounding boxes to identify original bounding boxes that are false positives, and generate an image file that includes the original bounding boxes, wherein those original bounding boxes that are identified as false positives are removed.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZJANSU3OyMssLE0tVkjLL1JwSS1JTS7JzEtXCEmtKOFhYE1LzClO5YXS3AzKbq4hzh66qQX58anFBYnJqXmpJfGhwUYGRsaGlmYWBuaOhsbEqQIAU_QlAA</recordid><startdate>20230622</startdate><enddate>20230622</enddate><creator>BARZELAY, Udi</creator><creator>AZULAI, Ophir</creator><creator>NAPARSTEK, Oshri Pesah</creator><scope>EVB</scope></search><sort><creationdate>20230622</creationdate><title>Techniques for Detecting Text</title><author>BARZELAY, Udi ; AZULAI, Ophir ; NAPARSTEK, Oshri Pesah</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2023196807A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>BARZELAY, Udi</creatorcontrib><creatorcontrib>AZULAI, Ophir</creatorcontrib><creatorcontrib>NAPARSTEK, Oshri Pesah</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>BARZELAY, Udi</au><au>AZULAI, Ophir</au><au>NAPARSTEK, Oshri Pesah</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Techniques for Detecting Text</title><date>2023-06-22</date><risdate>2023</risdate><abstract>In some examples, a system for detecting text in an image includes a memory device to store a text detection model trained using images of up-scaled text, and a processor configured to perform text detection on an image to generate original bounding boxes that identify potential text in the image. The processor is also configured to generate a secondary image that includes up-scaled portions of the image associated with bounding boxes below a threshold size, and perform text detection on the secondary image to generate secondary bounding boxes that identify potential text in the secondary image. The processor is also configured to compare the original bounding boxes with the secondary bounding boxes to identify original bounding boxes that are false positives, and generate an image file that includes the original bounding boxes, wherein those original bounding boxes that are identified as false positives are removed.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2023196807A1
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
PHYSICS
title Techniques for Detecting Text
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T14%3A24%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=BARZELAY,%20Udi&rft.date=2023-06-22&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2023196807A1%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true